mistral-ocr

Extracts text from scanned images and digital PDFs.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Parlamento-ai/parlamento-ai --skill mistral-ocr-parlamento-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mistral-ocr
Source: https://github.com/Parlamento-ai/parlamento-ai/tree/main/skills/mistral-ocr
Command: npx skills add https://github.com/Parlamento-ai/parlamento-ai --skill mistral-ocr-parlamento-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the need for efficient text extraction from scanned or digital documents, saving time on manual transcriptions and data entry.

Core Features & Use Cases

  • OCR text extraction from images and PDFs for digitizing physical documents.
  • PDF to Markdown conversion enabling easy editing and annotation.
  • Use Case: Quickly digitize a scanned contract or invoice to edit or analyze data without manual retyping.

Quick Start

Provide an image or PDF file URL or upload a local file in base64 format, then request text extraction for immediate use.

Frequently Asked Questions about mistral-ocr

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text from a scanned PDF or image?

To extract text from a scanned PDF or image, provide a file URL or upload a local file in base64 format. This OCR process instantly digitizes physical documents or digital PDFs into editable text.

How do I convert PDF to Markdown for editing?

Converting PDF to Markdown is achieved through OCR text extraction. This facilitates easy editing and annotation of digitized contracts or invoices without manual retyping.

Does this OCR text extraction support multiple languages?

Yes, OCR text extraction supports multiple languages. It reliably handles various formats and languages to satisfy rapid text digitization needs in administrative, legal, or academic settings.

Can I digitize physical documents using local image uploads?

Yes, you can digitize physical documents by uploading a local image file in base64 format. This enables immediate text extraction for efficient data analysis workflows.

What is the best way to automate text digitization for administrative workflows?

Automating text digitization involves using OCR to extract content from scanned images and digital PDFs. This approach saves time on manual transcriptions and data entry in administrative environments.

Why do I need OCR for digital PDFs instead of direct text extraction?

OCR is needed for digital PDFs containing scanned image layers rather than embedded text. It recognizes text within images, enabling accurate digitization and reliable data analysis workflows.